Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 84 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.5871. Min Act: -0.1700

Data Index: 444811 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.6497. Min Act: -0.1700

Data Index: 155768 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.5558. Min Act: -0.1700

Data Index: 162630 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.4931. Min Act: -0.1700

Data Index: 870921 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.5244. Min Act: -0.1700

Data Index: 805082 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.4618. Min Act: -0.1700

Data Index: 277049 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.4618. Min Act: -0.1700

Data Index: 793486 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.4461. Min Act: -0.1700

Data Index: 175631 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.4147. Min Act: -0.1700

Data Index: 556977 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.4147. Min Act: -0.1700

Data Index: 777794 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.3834. Min Act: -0.1700

Data Index: 403736 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.3990. Min Act: -0.1700

Data Index: 687144 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.4147. Min Act: -0.1700

Data Index: 1032246 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.3834. Min Act: -0.1700

Data Index: 1078904 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.3990. Min Act: -0.1700

Data Index: 1254150 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.3834. Min Act: -0.1700

Data Index: 920603 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.3520. Min Act: -0.1700

Data Index: 535860 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.3834. Min Act: -0.1700

Data Index: 240300 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.3677. Min Act: -0.1700

Data Index: 72557 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 3.6497. Min Range: -3.6497

Max Act: 3.3363. Min Act: -0.1700

Data Index: 943284 (C4 (Web Text))

Max Activating Token Index: 677